This repo is my attempt to get familiar to the field of regression by attempting the Housing Price Prediction competition on Kaggle.
I perform data cleaning, feature extraction using Boruta
and PCA
so that data is ready to be fed to regression models.
I have tried to compare the performance of various models such as linear regression
, tree
, random forest
and xgboost
to understand how they perform and estimate gain in performance if any. This exercise has helped me understand the implementation of these different models in R.